// RUN โ€” FITS

Can the NVIDIA GeForce RTX 4090 run Nanbeige-16B?

Yes โ€” here's how fast and up to what context, with real measured numbers.

Nanbeige-16B on the NVIDIA GeForce RTX 4090

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 yes 17k 46-54.8 t/s ~1.8-2.2 (slow)
Q4 yes 44k 82.1-97.9 t/s ~3.3-3.9 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to system RAM offload (depends on your system RAM) and speed drops to the "beyond" figure.

FAQ

Can the NVIDIA GeForce RTX 4090 run Nanbeige-16B?โ–ถ

Yes. At Q4 it generates ~82.1-97.9 tok/s and fits up to 44k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~3.3-3.9 tok/s.

How much context fits?โ–ถ

At Q4, up to about 44k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.